Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Oikonomou, Argyris"'
Many alignment methods, including reinforcement learning from human feedback (RLHF), rely on the Bradley-Terry reward assumption, which is insufficient to capture the full range of general human preferences. To achieve robust alignment with general p
Externí odkaz:
http://arxiv.org/abs/2410.23223
Autor:
Kalavasis, Alkis, Karbasi, Amin, Oikonomou, Argyris, Sotiraki, Katerina, Velegkas, Grigoris, Zampetakis, Manolis
As ML models become increasingly complex and integral to high-stakes domains such as finance and healthcare, they also become more susceptible to sophisticated adversarial attacks. We investigate the threat posed by undetectable backdoors, as defined
Externí odkaz:
http://arxiv.org/abs/2406.05660
Autor:
Li, Yingkai, Oikonomou, Argyris
We study a single-agent contracting environment where the agent has misspecified beliefs about the outcome distributions for each chosen action. First, we show that for a myopic Bayesian learning agent with only two possible actions, the empirical fr
Externí odkaz:
http://arxiv.org/abs/2405.20423
Autor:
Cai, Yang, Jordan, Michael I., Lin, Tianyi, Oikonomou, Argyris, Vlatakis-Gkaragkounis, Emmanouil-Vasileios
Numerous applications in machine learning and data analytics can be formulated as equilibrium computation over Riemannian manifolds. Despite the extensive investigation of their Euclidean counterparts, the performance of Riemannian gradient-based alg
Externí odkaz:
http://arxiv.org/abs/2306.16617
We study constrained comonotone min-max optimization, a structured class of nonconvex-nonconcave min-max optimization problems, and their generalization to comonotone inclusion. In our first contribution, we extend the Extra Anchored Gradient (EAG) a
Externí odkaz:
http://arxiv.org/abs/2206.05248
The monotone variational inequality is a central problem in mathematical programming that unifies and generalizes many important settings such as smooth convex optimization, two-player zero-sum games, convex-concave saddle point problems, etc. The ex
Externí odkaz:
http://arxiv.org/abs/2204.09228
We study revenue maximization in multi-item multi-bidder auctions under the natural item-independence assumption - a classical problem in Multi-Dimensional Bayesian Mechanism Design. One of the biggest challenges in this area is developing algorithms
Externí odkaz:
http://arxiv.org/abs/2111.03962
Autor:
Cai, Yang, Oikonomou, Argyris
We study the problem of selling $n$ heterogeneous items to a single buyer, whose values for different items are dependent. Under arbitrary dependence, Hart and Nisan show that no simple mechanism can achieve a non-negligible fraction of the optimal r
Externí odkaz:
http://arxiv.org/abs/2106.10814
We consider the black-box reduction from multi-dimensional revenue maximization to virtual welfare maximization. Cai et al. show a polynomial-time approximation-preserving reduction, however, the mechanism produced by their reduction is only approxim
Externí odkaz:
http://arxiv.org/abs/1911.10172
We study monotone inclusions and monotone variational inequalities, as well as their generalizations to non-monotone settings. We first show that the Extra Anchored Gradient (EAG) algorithm, originally proposed by Yoon and Ryu [2021] for unconstraine
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0205efee3ecfad53d99fcc22be4aa62a